4,893 件 ・ 関連度順
概要と使いどころ
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
日本語の概要は準備中です。原文の説明を表示しています。
Professional assistant for 3D printing, laser engraving, and 3D modeling workflows. Supports generating visual references for sculpting (Forger/ZBrush), creating 3D models via Meshy AI, and optimizing FDM/Resin print settings. Use when designing, fabricating, or troubleshooting physical maker projects.
日本語の概要は準備中です。原文の説明を表示しています。
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
日本語の概要は準備中です。原文の説明を表示しています。
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
日本語の概要は準備中です。原文の説明を表示しています。
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
日本語の概要は準備中です。原文の説明を表示しています。
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
日本語の概要は準備中です。原文の説明を表示しています。
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
日本語の概要は準備中です。原文の説明を表示しています。
Search personal knowledge bases, notes, docs, and meeting transcripts locally using qmd — a hybrid retrieval engine with BM25, vector search, and LLM reranking. Supports CLI and MCP integration.
日本語の概要は準備中です。原文の説明を表示しています。
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
日本語の概要は準備中です。原文の説明を表示しています。
Inspect, benchmark, and monitor Web3 RPC endpoints — latency checks, method support, chain detection, and health scoring.
日本語の概要は準備中です。原文の説明を表示しています。
Develop Burp Suite extensions in Java (Montoya API) or Python (Jython). Supports creating HTTP listeners, scanner checks, intruder payloads, UI tabs, and context menus. Includes project templates, multi-platform setup guides, and best practices.
日本語の概要は準備中です。原文の説明を表示しています。
Expert startup business analyst specializing in market sizing, financial modeling, competitive analysis, and strategic planning for early-stage companies. Use PROACTIVELY when the user asks about market opportunity, TAM/SAM/SOM, financial projections, unit economics, competitive landscape, team planning, startup metrics, or business strategy for pre-seed through Series A startups.
日本語の概要は準備中です。原文の説明を表示しています。
Analyzes and optimizes content structure including header hierarchy, suggests schema markup, and internal linking opportunities. Creates search-friendly content organization. Use PROACTIVELY for content structuring.
日本語の概要は準備中です。原文の説明を表示しています。
You are a cloud cost optimization expert specializing in reducing infrastructure expenses while maintaining performance and reliability. Analyze cloud spending, identify savings opportunities, and implement cost-effective architectures across AWS, Azure, and GCP.
日本語の概要は準備中です。原文の説明を表示しています。
Using Bogus to generate realistic fake data specialized skill. Used when generating realistic names, addresses, phone numbers, emails, company info and other test data. Covers Faker class, multi-language support, custom rules, bulk data generation, etc. Keywords: bogus, faker, fake data, fake data, realistic data, realistic data, fake name, fake address, fake email, Faker<T>, RuleFor, Generate, faker.Name, faker.Address, faker.Internet, generate fake data, generate fake data, seed data
日本語の概要は準備中です。原文の説明を表示しています。
Complete guide for TUnit new-generation testing framework. Use when creating test projects with TUnit or migrating from xUnit to TUnit. Covers Source Generator driven test discovery, AOT compilation support, fluent async assertions. Includes project creation, [Test] attribute, lifecycle management, parallel control, and xUnit syntax comparison. Keywords: TUnit, tunit testing, source generator testing, AOT testing, new generation testing framework, [Test], [Arguments], TUnit.Assertions, Assert.That, Before(Test), After(Test), NotInParallel, TUnit.Templates, Microsoft.Testing.Platform, TUnit vs xUnit, parallel execution
日本語の概要は準備中です。原文の説明を表示しています。
Evaluates and selects Threat Intelligence Platform (TIP) products based on organizational requirements including feed integration capability, STIX/TAXII support, workflow automation, analyst interface, and total cost of ownership. Use when conducting a TIP procurement, migrating between TIP solutions, or assessing whether the current TIP meets program maturity requirements. Activates for requests involving ThreatConnect, MISP, OpenCTI, Anomali, EclecticIQ, or TIP procurement decisions.
日本語の概要は準備中です。原文の説明を表示しています。
Detects AI-generated deepfake audio used in voice phishing (vishing) attacks by extracting spectral features (MFCC, spectral centroid, spectral contrast, zero-crossing rate) and classifying samples with machine learning models. Supports batch analysis of audio files, generates confidence scores, and produces forensic reports. Activates for requests involving deepfake voice detection, vishing investigation, AI-generated speech analysis, voice cloning detection, or audio authenticity verification.
日本語の概要は準備中です。原文の説明を表示しています。
Analyzes encryption algorithms, key management, and file encryption routines used by ransomware families to assess decryption feasibility, identify implementation weaknesses, and support recovery efforts. Covers AES, RSA, ChaCha20, and hybrid encryption schemes. Activates for requests involving ransomware cryptanalysis, encryption analysis, key recovery assessment, or ransomware decryption feasibility.
日本語の概要は準備中です。原文の説明を表示しています。
Build and configure a resilient command-and-control infrastructure using BishopFox's Sliver C2 framework with redirectors, HTTPS listeners, and multi-operator support for authorized red team engagements.
日本語の概要は準備中です。原文の説明を表示しています。
Traces ransomware cryptocurrency payment flows using blockchain analysis tools such as Chainalysis Reactor, WalletExplorer, and blockchain.com APIs. Identifies wallet clusters, tracks fund movement through mixers and exchanges, and supports law enforcement attribution. Activates for requests involving ransomware payment tracing, bitcoin wallet analysis, cryptocurrency forensics, or blockchain intelligence gathering.
日本語の概要は準備中です。原文の説明を表示しています。
Captures and analyzes network packet data using Wireshark and tshark to identify malicious traffic patterns, diagnose protocol issues, extract artifacts, and support incident response investigations on authorized network segments.
日本語の概要は準備中です。原文の説明を表示しています。
Analyzes RAM memory dumps from compromised systems using the Volatility framework to identify malicious processes, injected code, network connections, loaded modules, and extracted credentials. Supports Windows, Linux, and macOS memory forensics. Activates for requests involving memory forensics, RAM analysis, volatile data examination, process injection detection, or memory-resident malware investigation.
日本語の概要は準備中です。原文の説明を表示しています。
Scan the project for refactoring opportunities, then fix them. No behavior/visual changes.
日本語の概要は準備中です。原文の説明を表示しています。